International Business Machines Corporation

Kyndryl, Inc.

Renata Balthazar De Lima Mussauer

Helio Leonardo Pinheiro E Mota

Rosana Rueda Elias

Rafael Risso Moleiro

Breno H Leitao

Marcos Vinicius L Paraiso

Thiago Rodrigues De Souza Costa

Matheus Bitencourt Rangel Dantas

Priscila Vieira De Sousa

Michael Anthonny Paulino

Reginaldo Marcelo Dos Santos

While it is well known to power traffic control devices (for example, traffic lights) by an alternative energy source during power outages, some embodiments of the present invention additionally have: (i) a set of control computer(s), remote from the various traffic control devices, that is powered by an alternative energy source during a power outage; and/or (ii) a communication network, for communications between the set of control computer(s) and the various traffic control devices, that is powered by an alternative power source during a power outage. The use of alternative power to power the control computer(s) (for example, a hub) and/or the communication network allows the traffic control devices to continue to operate in a coordinated manner as instructed by the control computers, thereby avoiding a situation where the traffic lights begin operating independently of each other during a power outage.

Prediction method for resilient interconnected traffic management

A computer-implemented method to identify unauthorized use of a device based on a usage pattern. The method includes tracking usage of a device, wherein the usage includes activity by a user interacting with the device. The method includes identifying a usage pattern, wherein the usage pattern is based on usage data. The method further includes generating, based on the usage pattern, a heatmap. The method includes predicting future usage of the device by the user, wherein the predicting includes generating a Markov chain of the predicted future usage. The method also includes determining actual usage is different than the predicted usage. The method further includes calculating, in response to determining the actual usage is different than the predicted future usage, a difference score. The method includes determining the difference score is above a difference threshold, and activating, in response to the difference score being above the difference threshold, an alert.

Identifying anomolous device usage based on usage patterns

Authenticating a message by receiving a first message from a source, generating a touch activation matrix from the first message, the touch activation matrix comprising touchscreen data associated with the first message, generating a second message from the touch activation matrix, determining a first legitimacy state by comparing the first message and the second message, determining a second legitimacy state using a discriminator network, determining a categorization for the first message according to the first and second legitimacy states, and sending the categorization for the first message to the source.

Message authentication using generative adversarial networks

Embodiments describe an approach for generating a sign language translation of an audio portion of a video. Embodiments receive a request for a sign language translation for a selected video and extract audio from the selected video. Additionally, embodiments, convert the extracted audio into text, identify contextual sounds in the audio, and convert the text and the contextual sounds into sign language content. Furthermore, embodiments, generate a sign language video based on the sign language content, and display the sign language video in a separate display window on the selected video.

Generating visual closed caption for sign language

Growing community of inventors

Rio de Janeiro, Brazil

Renata Balthazar De Lima Mussauer